titleQwen-RobotNav Technical Report: A Scalable Navigation Model Designed for an Agentic Navigation System
authorsJiazhao Zhang, Gengze Zhou, Hale Yin, Yiyang Huang, Zixing Lei, Qihang Peng, Haoqi Yuan, Jie Zhang, Xudong Guo, Xiaoyue Chen, An Yang, Fei Huang, Zhibo Yang, Junyang Lin, Dayiheng Liu, Jingren Zhou, Zhuoyuan Yu, Jingyang Fan, Zhixuan Liang, Pei Lin, Ye Wang, Anzhe Chen, Kun Yan, Xiao Xu, Jiahao Li, Lulu Hu, Minying Zhang, Shurui Li, Wenhu Xiao, Shuai Bai, Xuancheng Ren, Chenxu Lv, Chenfei Wu, Xiong-Hui Chen
date2026-06-18
venuearXiv (preprint, not peer reviewed)
idarXiv:2606.18112
affiliationQwen
upvotes30 (Hugging Face Daily Papers, 2026-11-01)
linksabs pdf hf code
abstractAgentic navigation systems require a base navigation model whose observation strategy can be externally reconfigured at inference time, because instruction following, object search, target tracking, and autonomous driving share the same perception-planning backbone yet demand fundamentally different strategies for consuming the visual stream. We present Qwen-RobotNav, a scalable navigation model built on Qwen-RobotNav that addresses it through a parameterised interface with two complementary dimensions: multiple task modes that select the navigation behaviour, and controllable observation parameters (e.g., token budget, per-camera weights) that govern how visual history is encoded. With training-time randomization over all parameters, Qwen-RobotNav is robust to any inference-time configuration requiring zero architectural modification to the Qwen-RobotNav backbone. We train Qwen-RobotNav on 15.6M samples; co-training with vision-language data prevents the collapse into reactive action-sequence mappers observed in trajectory-only training. The parameterised interface also makes Qwen-RobotNav a natural building block for agentic systems: for long-horizon scenarios, an upper-level planner decomposes goals into sub-tasks and dynamically switches Qwen-RobotNav's task mode and context strategy mid-episode, composing complex behaviours from repeated calls to the same model. Extensive experiments show that Qwen-RobotNav sets new state-of-the-art results across major navigation benchmarks. The model exhibits favourable scaling from 2B to 8B parameters, with joint multi-task training developing a shared spatial-planning substrate that transfers across task families, and demonstrates strong zero-shot generalisation to real-world robots across diverse environments.

cite

@misc{zhang2026qwen,
  title={Qwen-RobotNav Technical Report: A Scalable Navigation Model Designed for an Agentic Navigation System},
  author={Jiazhao Zhang and Gengze Zhou and Hale Yin and Yiyang Huang and Zixing Lei and Qihang Peng and Haoqi Yuan and Jie Zhang and Xudong Guo and Xiaoyue Chen and An Yang and Fei Huang and Zhibo Yang and Junyang Lin and Dayiheng Liu and Jingren Zhou and Zhuoyuan Yu and Jingyang Fan and Zhixuan Liang and Pei Lin and Ye Wang and Anzhe Chen and Kun Yan and Xiao Xu and Jiahao Li and Lulu Hu and Minying Zhang and Shurui Li and Wenhu Xiao and Shuai Bai and Xuancheng Ren and Chenxu Lv and Chenfei Wu and Xiong-Hui Chen},
  year={2026},
  eprint={2606.18112},
  archivePrefix={arXiv},
  url={https://arxiv.org/abs/2606.18112}
}